blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-01-11 04:46:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: blackteay:cddd78f31873e126a595e241b7d64da686dfe539
Branches Tags
blackteay:main
blackteay:revert-1660-main
blackteay:fast_inference_
blackteay:20250606v2pro
blackteay:20250422v4
blackteay:20250228v3
blackteay:20240821v2
..
compare: blackteay:784d7d1cbb1b6565df69e864beabad6409ba484b
Branches Tags
blackteay:main
blackteay:revert-1660-main
blackteay:fast_inference_
blackteay:20250606v2pro
blackteay:20250422v4
blackteay:20250228v3
blackteay:20240821v2

4 Commits
cddd78f318 ... 784d7d1cbb

Author SHA1 Message Date
Spr_Aachen
784d7d1cbb
Merge 35fac290ba937d032f9b635a14abf667037a1dcb into c767f0b83b998e996a4d230d86da575a03f54a3f 2026-01-05 09:48:03 +08:00
ChasonJiang
c767f0b83b
修复bug (#2704) 
* 修复bug

* fallbak and bug fix
 2025-12-30 16:00:21 +08:00
ChasonJiang
9080a967d5
修复采样错误 (#2703) 2025-12-30 15:21:03 +08:00
sushistack
51df9f7384
Fix model file name in README instructions (#2700) 2025-12-25 16:44:21 +08:00
2 changed files with 2 additions and 3 deletions
Show Stats Expand all files Collapse all files

3
GPT_SoVITS/AR/models/t2s_model.py
View File

@ -707,12 +707,11 @@ class Text2SemanticDecoder(nn.Module):
if idx == 0: if idx == 0:
attn_mask = F.pad(attn_mask[:, :, -1].unsqueeze(-2), (0, 1), value=False) attn_mask = F.pad(attn_mask[:, :, -1].unsqueeze(-2), (0, 1), value=False)
logits = logits[:, :-1]
else: else:
attn_mask = F.pad(attn_mask, (0, 1), value=False) attn_mask = F.pad(attn_mask, (0, 1), value=False)
if idx < 11: ###至少预测出10个token不然不给停止（0.4s） if idx < 11: ###至少预测出10个token不然不给停止（0.4s）
logits = logits[:, :-1] logits = logits[:, :-1]
samples = sample( samples = sample(
logits, y, top_k=top_k, top_p=top_p, repetition_penalty=repetition_penalty, temperature=temperature logits, y, top_k=top_k, top_p=top_p, repetition_penalty=repetition_penalty, temperature=temperature

2
README.md
View File

@ -347,7 +347,7 @@ Use v4 from v1/v2/v3 environment:
2. Clone the latest codes from github. 2. Clone the latest codes from github.
3. Download v4 pretrained models (gsv-v4-pretrained/s2v4.ckpt, and gsv-v4-pretrained/vocoder.pth) from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main) and put them into `GPT_SoVITS/pretrained_models`. 3. Download v4 pretrained models (gsv-v4-pretrained/s2v4.pth, and gsv-v4-pretrained/vocoder.pth) from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main) and put them into `GPT_SoVITS/pretrained_models`.
## V2Pro Release Notes ## V2Pro Release Notes